AlphaGo教案资料.pptx

AlphaGO,Deep-learning,software defeats human,professional,for first time.,What is AlphaGO,AlphaGo is a computer program developed by Google DeepMind in London to play the board game Go.,AlphaGos algorithm uses a combination of neural networks,machine learning and Monte Carlo tree search techniques,combined with extensive training,both from human and computer play.,Why the game of Go,10,170,1919,150,Go is considered much more difficult for computers to win than other games such as chess,because its much larger branching factor makes it prohibitively difficult to use traditional AI,methods.,In China,Japan and South Korea,Go is hugely popular and is even played by celebrity professionals,.,The,average 150-move game contains more possible board configurations,than the atoms,in the,Universe.,Competitions,In October 2015,the distributed version of AlphaGo defeated the European Go champion Fan,Hui,a 2-dan professional,five to zero.,This was the first time a computer Go program had beaten a professional human player on a full-sized board without handicap.,Match against Lee,Sedol,AlphaGo has,defeated Korean grandmaster Lee Sedol,finishing the best-of-five series with four wins and one loss,.,2,1,Lee,Sedol had the second-highest number of Go international championship victories in,the world.,But after this competition,AlphaGo replaces his ranking.,Responses to,victory,milestone,progress,AlphaGos March 2016 victory was a major milestone in artificial intelligence research,.,Go had previously been regarded as a hard problem in machine learning that was expected to be out of reach for the technology of the time.When compared with Deep,Blue,AlphaGos underlying algorithms are potentially more general-purpose,and may be evidence that the scientific community is making progress toward artificial general intelligence.,